Package: nn2poly 0.1.2
nn2poly: Neural Network Weights Transformation into Polynomial Coefficients
Implements a method that builds the coefficients of a polynomial model that performs almost equivalently as a given neural network (densely connected). This is achieved using Taylor expansion at the activation functions. The obtained polynomial coefficients can be used to explain features (and their interactions) importance in the neural network, therefore working as a tool for interpretability or eXplainable Artificial Intelligence (XAI). See Morala et al. 2021 <doi:10.1016/j.neunet.2021.04.036>, and 2023 <doi:10.1109/TNNLS.2023.3330328>.
Authors:
nn2poly_0.1.2.tar.gz
nn2poly_0.1.2.tar.gz(r-4.5-noble)nn2poly_0.1.2.tar.gz(r-4.4-noble)
nn2poly_0.1.2.tgz(r-4.4-emscripten)nn2poly_0.1.2.tgz(r-4.3-emscripten)
nn2poly.pdf |nn2poly.html✨
nn2poly/json (API)
NEWS
# Install 'nn2poly' in R: |
install.packages('nn2poly', repos = c('https://cran.r-universe.dev', 'https://cloud.r-project.org')) |
Bug tracker:https://github.com/ibidat/nn2poly/issues
Pkgdown:https://ibidat.github.io
Last updated 30 days agofrom:4f87bea040. Checks:OK: 1 NOTE: 1. Indexed: no.
Target | Result | Date |
---|---|---|
Doc / Vignettes | OK | Nov 25 2024 |
R-4.5-linux-x86_64 | NOTE | Nov 25 2024 |
Exports:add_constraintsfitluz_model_sequentialnn2poly
Dependencies:genericsmatrixStatspracmaRcppRcppArmadillo
Classification example using tensorflow
Rendered fromnn2poly-03-classification-example.Rmd
usingknitr::rmarkdown
on Nov 25 2024.Last update: 2024-01-25
Started: 2024-01-25
Introduction to nn2poly
Rendered fromnn2poly-01-introduction.Rmd
usingknitr::rmarkdown
on Nov 25 2024.Last update: 2024-11-11
Started: 2024-01-25
Supported DL frameworks
Rendered fromnn2poly-02-supported-DL-frameworks.Rmd
usingknitr::rmarkdown
on Nov 25 2024.Last update: 2024-11-11
Started: 2024-01-25
Readme and manuals
Help Manual
Help page | Topics |
---|---|
Add constraints to a neural network | add_constraints |
Polynomial evaluation | eval_poly |
Build a 'luz' model composed of a linear stack of layers | luz_model_sequential |
Obtain polynomial representation | nn2poly |
Plots a comparison between two sets of points. | plot_diagonal |
Plots activation potentials and Taylor expansion. | plot_taylor_and_activation_potentials |
Plot method for 'nn2poly' objects. | plot.nn2poly |
Predict method for 'nn2poly' objects. | predict.nn2poly |